arXiv subjects

Zhaoqing Li

Publications and source records attributed to Zhaoqing Li.

At least 19 recordsLinked to original sources

arXiv2026

Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering

This paper presents a novel data-free and training-free compression approach for speech foundation models using channelwise clustering via k-means. More fine-grained, mixed sparsity pruning by layer-level varying number of parameter clusters is also explored. Experiments conducted on the LibriSpeech dataset suggest that when operating with pruning sparsity of 50% on HuBERT-large, consistent WER reductions of 27.73%/18.61% absolute (34.37%/21.91% relative) over the magnitude-based pruning were obtained on the test-clean and test-other subsets before fine-tuning and 0.19%/0.79% absolute (3.36%/4.62% relative) after fine-tuning with only 3 epochs. Similar WER reductions of 2.86%/5.02% absolute (59.21%/55.29% relative) were observed against magnitudebased pruning on Whisper-large-v3 at 10% sparsity, all with no significant WER increase relative to the uncompressed baseline.

cs.SD↗

arXiv2026

UNISON: A Unified Sound Generation and Editing Framework via Deep LLM Fusion

We present UNISON, a latent diffusion framework that unifies speech generation, sound generation, and audio editing within a single model. A single model handles text-to-audio, text-to-speech, zero-shot speaker cloning, mixed speech-and-sound generation, scene-level audio editing, speech-in-scene editing, and timed temporal composition, all of which share a single set of weights. Our architecture features two core designs: (1) Layer-wise deep LLM fusion, which injects hidden states from uniformly sampled layers of a frozen MLLM into corresponding MM-DiT blocks via learned projections, providing depth-matched semantic conditioning that improves instruction following over single-layer baselines; and (2) a unified multi-task architecture where task identity is encoded solely by a channel-wise mask and source audio is provided through VAE-encoded channel concatenation. Training is stabilized by an online GPU-side multi-task data synthesis pipeline with task-homogeneous batching and a two-stage curriculum. With 621M--732M trainable parameters, UNISON achieves results competitive with or exceeding task-specialist models across evaluated domains, while being roughly $4\times$ smaller than comparable unified systems.

eess.AS↗

arXiv2026

Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm

Humans often specify and create through visual artifacts: typography sheets, sketches, reference images, and annotated scenes. Yet modern visual generators still ask users to serialize this intent into text, a bottleneck that compresses signals like spatial structure, exact appearance, and glyph shape. We propose \textbf{\emph{visual-to-visual} (V2V)} generation, in which the user conditions a generative model with a visual specification page rather than a text prompt. The page is not an edit target, but a visual document that specifies the desired output. We introduce \textbf{V2V-Zero}, a training-free framework that exposes this interface in existing vision-language model (VLM) conditioned generators by replacing text-only conditioning with final-layer hidden states extracted from visual pages, exploiting the fact that the frozen VLM already maps both text and images into the generator's conditioning space. On GenEval, V2V-Zero reaches 0.85 with a frozen Qwen-Image backbone, closely matching its optimized text-to-image performance without fine-tuning. To evaluate the broader V2V space, we introduce \textbf{Simple-V2V Bench}, spanning seven visual-conditioning tasks and seven models, including GPT Image 2, Nano Banana 2, Seedream 5.0 Lite, open-weight baselines, and a video extension. V2V-Zero scores 32.7/100, outperforming evaluated open-weight image baselines and revealing a clear capability hierarchy: attribute binding is strong, content generation is unreliable, and structural control remains hard even for commercial systems. A HunyuanVideo-1.5 extension scores 20.2/100, showing the interface transfers beyond images. Mechanistic analysis shows the default reasoning path is primarily visually routed, with 95.0\% of conditioning-token attention mass on visual-page hidden states.

cs.CV↗

arXiv2026

SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis

Continuous autoregressive speech synthesis has recently emerged as a promising direction for zero-shot text-to-speech (TTS). However, existing methods still suffer from a fundamental mismatch between semantic-prosodic modeling and reconstruction-driven continuous speech representations. This mismatch causes TTS models to focus excessively on low-level acoustic textures at the expense of high-level semantic coherence, further exacerbating error accumulation in autoregressive generation. To address this challenge, we propose SemaVoice, a semantic-aware continuous autoregressive framework for high-fidelity zero-shot TTS. SemaVoice introduces a Speech Foundation Model (SFM) guided alignment mechanism that refines continuous speech representations to better capture both local semantic consistency and global structural relationships. These representations condition a patch-wise diffusion head within the autoregressive framework for high-quality speech synthesis. Experimental results on the Seed-TTS benchmark show that SemaVoice achieves an English WER of 1.71\% and remains highly competitive with state-of-the-art open-source systems in both objective and subjective evaluations. The effectiveness of SFM guided alignment is further confirmed by significant improvements under varying representation granularities with a fixed information-rate constraint.

eess.AS↗

arXiv2026

ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching

Generating spoken dialogue is inherently more complex than monologue text-to-speech (TTS), as it demands both realistic turn-taking and the maintenance of distinct speaker timbres. While existing autoregressive (AR) models have made progress, they often suffer from high inference latency and stability issues. To overcome these limitations, we propose ZipVoice-Dialog, a non-autoregressive (NAR) zero-shot spoken dialogue generation model based on flow-matching. Observing that applying vanilla flow-matching to dialogue generation leads to poor speech intelligibility and turn-taking precision, we introduce two simple yet effective methods to adapt flow-matching architectures for dialogue generation: (1) a curriculum learning strategy to ensure robust speech-text alignment, and (2) speaker-turn embeddings to govern precise speaker turn-taking. Additionally, we introduce dedicated strategies to support stereo dialogue generation. Recognizing the lack of training datasets in this field, we curate and release OpenDialog, the first large-scale (6.8k hours) open-source spoken dialogue dataset derived from in-the-wild speech data. Moreover, for fair and rigorous evaluations, we established a benchmark to comprehensively evaluate dialogue generation models. Experiments demonstrate the effectiveness of the proposed methods and dataset, showing that ZipVoice-Dialog achieves superior performance in inference speed, intelligibility, speaker turn-taking accuracy, and speaker similarity. Our code, model checkpoints, and the OpenDialog dataset are publicly available at https://github.com/k2-fsa/ZipVoice.

eess.AS↗

arXiv2026

Flow2GAN: Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-step High-Fidelity Audio Generation

Existing dominant methods for audio generation include Generative Adversarial Networks (GANs) and diffusion-based methods like Flow Matching. GANs suffer from slow convergence during training, while diffusion methods require multi-step inference that introduces considerable computational overhead. In this work, we introduce Flow2GAN, a two-stage framework that combines Flow Matching training for learning generative capabilities with GAN fine-tuning for efficient few-step inference. Specifically, given audio's unique properties, we first improve Flow Matching for audio modeling through: 1) reformulating the objective as endpoint estimation, avoiding velocity estimation difficulties when involving empty regions; 2) applying spectral energy-based loss scaling to emphasize perceptually salient quieter regions. Building on these Flow Matching adaptations, we demonstrate that a further stage of lightweight GAN fine-tuning enables us to obtain few-step (e.g., 1/2/4 steps) generators that produce high-quality audio. In addition, we develop a multi-branch network architecture that processes Fourier coefficients at different time-frequency resolutions, which improves the modeling capabilities compared to prior single-resolution designs. Experimental results indicate that our Flow2GAN delivers high-fidelity audio generation from Mel-spectrograms or discrete audio tokens, achieving highly favorable quality-efficiency trade-offs compared to existing state-of-the-art GAN-based and Flow Matching-based methods. Online demo samples are available at https://flow2gan.github.io, and the source code is released at https://github.com/k2-fsa/Flow2GAN.

eess.AS↗

arXiv2026

Multi-Channel Speech Enhancement for Cocktail Party Speech Emotion Recognition

This paper highlights the critical importance of multi-channel speech enhancement (MCSE) for speech emotion recognition (ER) in cocktail party scenarios. A multi-channel speech dereverberation and separation front-end integrating DNN-WPE and mask-based MVDR is used to extract the target speaker's speech from the mixture speech, before being fed into the downstream ER back-end using HuBERT- and ViT-based speech and visual features. Experiments on mixture speech constructed using the IEMOCAP and MSP-FACE datasets suggest the MCSE output consistently outperforms domain fine-tuned single-channel speech representations produced by: a) Conformer-based metric GANs; and b) WavLM SSL features with optional SE-ER dual task fine-tuning. Statistically significant increases in weighted, unweighted accuracy and F1 measures by up to 9.5%, 8.5% and 9.1% absolute (17.1%, 14.7% and 16.0% relative) are obtained over the above single-channel baselines. The generalization of IEMOCAP trained MCSE front-ends are also shown when being zero-shot applied to out-of-domain MSP-FACE data.

cs.SD↗

arXiv2025

Ferromagnetic interface engineering of spin-charge conversion in RuO$_2$

Spin-orbit torque efficiency is conventionally fixed by bulk materials. $D$-wave altermagnets introduce an additional nonrelativistic spin-charge conversion channel beyond inverse spin-Hall effect. Using prototypical candidate RuO$_2$ as an example, we show that the adjacent ferromagnet alone can dictate both the magnitude and sign of spin-charge conversion. Spin-pumping measurements on RuO$_2$/Y$_3$Fe$_5$O$_{12}$ (YIG) and RuO$_2$/Ni$_{80}$Fe$_{20}$ (Py) bilayers yield opposite effective spin-Hall angles that persist across crystalline and polycrystalline RuO$_2$. Inserting an ultrathin Au spacer at the RuO$_2$/YIG interface reverses the signal, envidencing a dominant interfacial inverse Rashba-Edelstein effect, whereas RuO$_2$/Py is governed by bulk inverse spin-Hall effect. First-principles calculations trace this dichotomy to interface-selective band hybridization: Rashba surface states survive at the insulating YIG contact yet are quenched by metallic Py. Our findings establish ferromagnetic interfacing as a deterministic knob for tailoring spin-charge conversion in altermagnetic oxides, paving the way to field-free, low-dissipation spintronic memory devices.

cond-mat.mtrl-sci↗

arXiv2025

Towards Effective and Efficient Non-autoregressive decoders for Conformer and LLM-based ASR using Block-based Attention Mask

Automatic speech recognition (ASR) systems often rely on autoregressive (AR) Transformer decoder architectures, which limit efficient inference parallelization due to their sequential nature. To this end, non-autoregressive (NAR) approaches aim primarily to achieve significant decoding speedup while the maintaining recognition accuracy that is comparable to AR baselines. This paper proposes a novel NAR block-based attention mask decoder (AMD) that effectively improves decoding efficiency while maintaining ASR accuracy, and also offering flexibility in balancing the performance-efficiency trade-off on both Conformer and large language model (LLM)-based ASR systems. The proposed AMD performs parallel inference within contiguous blocks of output labels while maintaining monotonic left-to-right prediction between blocks. A one-pass beam search algorithm is designed to dynamically fuse Connectionist Temporal Classification (CTC), AR decoder, and AMD probabilities. Experiments are conducted on normal speech LS960 and DBank elderly speech across: a) The Conformer encoder-decoder ASR system with filterbank input features; b) its integration with WavLM features; and c) further advancement by integrating an LLM-based decoder. On the LS960 task, the proposed AMD empowered tripartite decoder achieves decoding speedup ratios of up to 1.44x, 1.55x, and 2.31x under the three model configurations over the CTC + AR baselines, without statistically significant WER increases. When operating with real-time factors (RTFs) comparable to the baselines, the tripartite decoder produces statistically significant WER reductions of 0.19%, 0.62% and 0.13% absolute (4.3%, 16.3%, and 3.8% relative). Similar improvements are also obtained on the DBank task.

eess.AS↗

arXiv2025

Exploring Cross-Utterance Speech Contexts for Conformer-Transducer Speech Recognition Systems

This paper investigates four types of cross-utterance speech contexts modeling approaches for streaming and non-streaming Conformer-Transformer (C-T) ASR systems: i) input audio feature concatenation; ii) cross-utterance Encoder embedding concatenation; iii) cross-utterance Encoder embedding pooling projection; or iv) a novel chunk-based approach applied to C-T models for the first time. An efficient batch-training scheme is proposed for contextual C-Ts that uses spliced speech utterances within each minibatch to minimize the synchronization overhead while preserving the sequential order of cross-utterance speech contexts. Experiments are conducted on four benchmark speech datasets across three languages: the English GigaSpeech and Mandarin Wenetspeech corpora used in contextual C-T models pre-training; and the English DementiaBank Pitt and Cantonese JCCOCC MoCA elderly speech datasets used in domain fine-tuning. The best performing contextual C-T systems consistently outperform their respective baselines using no cross-utterance speech contexts in pre-training and fine-tuning stages with statistically significant average word error rate (WER) or character error rate (CER) reductions up to 0.9%, 1.1%, 0.51%, and 0.98% absolute (6.0%, 5.4%, 2.0%, and 3.4% relative) on the four tasks respectively. Their performance competitiveness against Wav2vec2.0-Conformer, XLSR-128, and Whisper models highlights the potential benefit of incorporating cross-utterance speech contexts into current speech foundation models.

eess.AS↗

arXiv2025

ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching

Existing large-scale zero-shot text-to-speech (TTS) models deliver high speech quality but suffer from slow inference speeds due to massive parameters. To address this issue, this paper introduces ZipVoice, a high-quality flow-matching-based zero-shot TTS model with a compact model size and fast inference speed. Key designs include: 1) a Zipformer-based vector field estimator to maintain adequate modeling capabilities under constrained size; 2) Average upsampling-based initial speech-text alignment and Zipformer-based text encoder to improve speech intelligibility; 3) A flow distillation method to reduce sampling steps and eliminate the inference overhead associated with classifier-free guidance. Experiments on 100k hours multilingual datasets show that ZipVoice matches state-of-the-art models in speech quality, while being 3 times smaller and up to 30 times faster than a DiT-based flow-matching baseline. Codes, model checkpoints and demo samples are publicly available at https://github.com/k2-fsa/ZipVoice.

eess.AS↗

arXiv2025

Exploring SSL Discrete Speech Features for Zipformer-based Contextual ASR

Self-supervised learning (SSL) based discrete speech representations are highly compact and domain adaptable. In this paper, SSL discrete speech features extracted from WavLM models are used as additional cross-utterance acoustic context features in Zipformer-Transducer ASR systems. The efficacy of replacing Fbank features with discrete token features for modelling either cross-utterance contexts (from preceding and future segments), or current utterance's internal contexts alone, or both at the same time, are demonstrated thoroughly on the Gigaspeech 1000-hr corpus. The best Zipformer-Transducer system using discrete tokens based cross-utterance context features outperforms the baseline using utterance internal context only with statistically significant word error rate (WER) reductions of 0.32% to 0.41% absolute (2.78% to 3.54% relative) on the dev and test data. The lowest published WER of 11.15% and 11.14% were obtained on the dev and test sets. Our work is open-source and publicly available at https://github.com/open-creator/icefall/tree/master/egs/gigaspeech/Context\_ASR.

cs.CL↗

arXiv2025

Effective and Efficient One-pass Compression of Speech Foundation Models Using Sparsity-aware Self-pinching Gates

This paper presents a novel approach for speech foundation models compression that tightly integrates model pruning and parameter update into a single stage. Highly compact layer-level tied self-pinching gates each containing only a single learnable threshold are jointly trained with uncompressed models and used in fine-grained neuron level pruning. Experiments conducted on the LibriSpeech-100hr corpus suggest that our approach reduces the number of parameters of wav2vec2.0-base and HuBERT-large models by 65% and 60% respectively, while incurring no statistically significant word error rate (WER) increase on the test-clean dataset. Compared to previously published methods on the same task, our approach not only achieves the lowest WER of 7.05% on the test-clean dataset under a comparable model compression ratio of 4.26x, but also operates with at least 25% less model compression time.

cs.SD↗

arXiv2025

Unfolding A Few Structures for The Many: Memory-Efficient Compression of Conformer and Speech Foundation Models

This paper presents a novel memory-efficient model compression approach for Conformer ASR and speech foundation systems. Our approach features a unique "small-to-large" design. A compact "seed" model containing a few Conformer or Transformer blocks is trained and unfolded many times to emulate the performance of larger uncompressed models with different logical depths. The seed model and many unfolded paths are jointly trained within a single unfolding cycle. The KL-divergence between the largest unfolded and smallest seed models is used in a self-distillation process to minimize their performance disparity. Experimental results show that our foldable model produces ASR performance comparable to individually constructed Conformer and wav2vec2/HuBERT speech foundation models under various depth configurations, while requiring only minimal memory and storage. Conformer and wav2vec2 models with a reduction of 35% and 30% parameters are obtained without loss of performance, respectively.

cs.SD↗

arXiv2025

Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision

Model compression has become an emerging need as the sizes of modern speech systems rapidly increase. In this paper, we study model weight quantization, which directly reduces the memory footprint to accommodate computationally resource-constrained applications. We propose novel approaches to perform extremely low-bit (i.e., 2-bit and 1-bit) quantization of Conformer automatic speech recognition systems using multiple precision model co-training, stochastic precision, and tensor-wise learnable scaling factors to alleviate quantization incurred performance loss. The proposed methods can achieve performance-lossless 2-bit and 1-bit quantization of Conformer ASR systems trained with the 300-hr Switchboard and 960-hr LibriSpeech corpus. Maximum overall performance-lossless compression ratios of 16.2 and 16.6 times are achieved without a statistically significant increase in the word error rate (WER) over the full precision baseline systems, respectively.

cs.SD↗

arXiv2025

Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions

Recent advancements in large language models (LLMs) have revolutionized various domains, bringing significant progress and new opportunities. Despite progress in speech-related tasks, LLMs have not been sufficiently explored in multi-talker scenarios. In this work, we present a pioneering effort to investigate the capability of LLMs in transcribing speech in multi-talker environments, following versatile instructions related to multi-talker automatic speech recognition (ASR), target talker ASR, and ASR based on specific talker attributes such as sex, occurrence order, language, and keyword spoken. Our approach utilizes WavLM and Whisper encoder to extract multi-faceted speech representations that are sensitive to speaker characteristics and semantic context. These representations are then fed into an LLM fine-tuned using LoRA, enabling the capabilities for speech comprehension and transcription. Comprehensive experiments reveal the promising performance of our proposed system, MT-LLM, in cocktail party scenarios, highlighting the potential of LLM to handle speech-related tasks based on user instructions in such complex settings. The code, model, and samples are available at https://github.com/cuhealthybrains/MT-LLM.

cs.CL↗

arXiv2025

CR-CTC: Consistency regularization on CTC for improved speech recognition

Connectionist Temporal Classification (CTC) is a widely used method for automatic speech recognition (ASR), renowned for its simplicity and computational efficiency. However, it often falls short in recognition performance. In this work, we propose the Consistency-Regularized CTC (CR-CTC), which enforces consistency between two CTC distributions obtained from different augmented views of the input speech mel-spectrogram. We provide in-depth insights into its essential behaviors from three perspectives: 1) it conducts self-distillation between random pairs of sub-models that process different augmented views; 2) it learns contextual representation through masked prediction for positions within time-masked regions, especially when we increase the amount of time masking; 3) it suppresses the extremely peaky CTC distributions, thereby reducing overfitting and improving the generalization ability. Extensive experiments on LibriSpeech, Aishell-1, and GigaSpeech datasets demonstrate the effectiveness of our CR-CTC. It significantly improves the CTC performance, achieving state-of-the-art results comparable to those attained by transducer or systems combining CTC and attention-based encoder-decoder (CTC/AED). We release our code at https://github.com/k2-fsa/icefall.

eess.AS↗

arXiv2025

Effective and Efficient Mixed Precision Quantization of Speech Foundation Models

This paper presents a novel mixed-precision quantization approach for speech foundation models that tightly integrates mixed-precision learning and quantized model parameter estimation into one single model compression stage. Experiments conducted on LibriSpeech dataset with fine-tuned wav2vec2.0-base and HuBERT-large models suggest the resulting mixed-precision quantized models increased the lossless compression ratio by factors up to 1.7x and 1.9x over the respective uniform-precision and two-stage mixed-precision quantized baselines that perform precision learning and model parameters quantization in separate and disjointed stages, while incurring no statistically word error rate (WER) increase over the 32-bit full-precision models. The system compression time of wav2vec2.0-base and HuBERT-large models is reduced by up to 1.9 and 1.5 times over the two-stage mixed-precision baselines, while both produce lower WERs. The best-performing 3.5-bit mixed-precision quantized HuBERT-large model produces a lossless compression ratio of 8.6x over the 32-bit full-precision system.

cs.SD↗